Author/Authors :
ALPASLAN, Faruk Ondokuz Mayıs Üniversitesi - Fen Edebiyat Fakültesi - İstatistik Bölümü, Turkey , ERİLLİ, Necati Alp Ondokuz Mayıs Üniversitesi - Fen Edebiyat Fakültesi - İstatistik Bölümü, Turkey , YOLCU, Ufuk Ondokuz Mayıs Üniversitesi - Fen Edebiyat Fakültesi - İstatistik Bölümü, Turkey , EĞRİOĞLU, Erol Ondokuz Mayıs Üniversitesi - Fen Edebiyat Fakültesi - İstatistik Bölümü, Turkey , ALADAĞ, Ç. Hakan Hacettepe Üniversitesi - Fen Fakültesi - İstatistik Bölümü, Turkey
Title Of Article :
BULANIK KÜMELEMEDE EN UYGUN KÜME SAYISININ YAPAY SİNİR AĞLARI VE DİSKRİMİNANT ANALİZİ İLE BELİRLENMESİ
Abstract :
In a clustering problem, it would be better to use fuzzy clustering if there was an uncertainty in determining clusters or memberships of some units. Determining the number of cluster has an important role on obtaining sensible and sound results in clustering analysis. In many clustering algorithm, it is firstly need to know number of cluster. However, there is no pre information about the number of cluster in general. The process of determining the most proper number of cluster is called as cluster validation. In the available fuzzy clustering literature, the most proper number of cluster is determined by utilizing cluster validation indices. When the data contain complexity are being analyzed, cluster validation indices can produce conflictive results. Also, there is no criterion point out the best index. In this study, artificial neural networks and discriminant analysis are employed to determine the number of cluster and the proposed method are applied some data and obtained results are compared to those obtained from validation indices like PC and CE.
NaturalLanguageKeyword :
Fuzzy clustering , Cluster validation index , Artificial neural network , Discriminant analysis.
JournalTitle :
Journal Of Economics and Administrative Sciences, Ataturk University
